News for hackers. Stuff that matters.
Re:Building an early warning system for LLM-aided biological... by sjwhevvvvvsj on Wednesday January 31, 2024 @02:27PM (#39208154)
The definition of “best” has a lot of factors. Best general purpose LLM chat? I’d agree there, but there’s so much more to LLM than chat applications.

For some tasks I’m working on, Mixtral is the “best” solution given it can be used locally, isn’t hampered by “safety” tuning, and I can run it 24x7 on huge jobs with no costs besides the upfront investment on my GPU + electricity.

I have GPT-4 open all day as my coding assistant, but I’m deploying on Mixtral.

Re:Building an early warning system for LLM-aided biological... by danielmarkbruce on Wednesday January 31, 2024 @03:22PM (#39208860)
Yup, plenty of reasons to run your own model.

I'm not using GPT-4 for chat, but for what I'd class as "reasoning" applications. It seems best by a long shot. As for safety, I find with the api and the system prompt that there is nothing it won't answer for me. That being said... I'm not asking for anything weird. GPT-4 turbo does seem to be reluctant sometimes.

Re:Building an early warning system for LLM-aided biological... by sjwhevvvvvsj on Wednesday January 31, 2024 @04:53PM (#39209933)
I’m doing document summarization and classification, and there’s a fair amount it won’t do for prudish reasons (eg sex, porn, etc). Llama2 is basically useless in that regard.
Re:Building an early warning system for LLM-aided biological... by danielmarkbruce on Wednesday January 31, 2024 @05:22PM (#39210262)
with GPT-4 (non-turbo) and a good system prompt?
Re:Building an early warning system for LLM-aided biological... by sjwhevvvvvsj on Wednesday January 31, 2024 @08:45PM (#39211944)
It’s unpredictable, usually it behaves but on arbitrary web text you’ll eventually trigger a “safety” barrier, and sometimes just trying again will work.